Fair Recommenders and the Sequencing of Information and Deliberation

Carina Hausladen

Fair Feed Ranking for Participatory Budgeting

Carina Hausladen

Fair Feed Ranking for Participatory Budgeting

MünchenBudget

• Every proposal must be assessed for feasibility, legality, cost, and duplication.
  • Centralized review is
    costly and it
  • concentrates agenda-setting power.

Scale creates two problems

Vetting.

Scale creates two problems

• Every proposal must be assessed for feasibility, legality, cost, and duplication.
  • Centralized review is
    costly and it
  • concentrates agenda-setting power.

Scale creates two problems

sorting

filtering

• used by more than 200 public institutions
• in over 35 countries
• and serves more than 100 million people.

Cross-Platform-Comparison

Literature

• Getting citizens interested
  • beyond their own needs / their initial favorite
  • towards their communities' needs

• a third of Amazon purchases
• 70% of YouTube watch time and
• 80% of Netflix viewing

Learning from recommender systems

Learning from online communities

• Common characteristic: large option space
• Found ways to manage them effectively

FairFeed

1. Ranking process must be transparent
2. Address the vetting problem
3. Exposure correction / visibility floor

Data and Simulation

Data

Simulation

• 459 Proposals
• 7134 Voters
  • their decision
    • seed is supported automatically
    • each other proposal is supported as a combination of
      • fit
      • divisiveness
      • position
  • browsing length
    • rises with recent relevance and
    • falls with fatigue

Results

Munich field data, June 2026

Conclusion

• Participatory Budgeting has a scale problem

• Platform "solutions" partly aggravate the problem

• FairFeed combines
  • fair exposure
  • crowd-sourced-vetting through negative feedback
  • transparent ranking on explicit preferences

• FairFeed increases
  • browsing length and relevance
  • coverage
  • non-seed votes
  • and top 20 quality

Open Questions

• A user who lacks domain knowledge cannot state a preference over a feature until the system has shown them  some.
• Interviewing the participant over the pool itself:
  • showing a fixed set of (unrated) proposals to the user
  • the system chooses the one whose rating would teach it the most about the user 
• Example:
  • Eight turns, each turn shows one proposal, the participant rates it,
  • the scores over the pool are updated,
  • and the next proposal is picked against the updated scores.

How to improve the onboarding?

Other onboarding ideas?

For more ideas click here.

How to implement "transparency"?

• Learned preferences/ vote counts downloadable as .json?
• what else?

Is recommending interesting items enough?

More Fairness Criteria?

Should we keep categories?

Implementation

Where to find test data?

• https://datos.madrid.es/dataset/300593-0-participativos-ganadores
• Creative Commons Attribution 4.0 International (CC BY 4.0)

Appendix

Attention

• Citizens cannot realistically inspect thousands of proposals before voting.
• The set of proposals a voter encounters is shaped by
  • the voter’s entry point
  • the platform’s ordering rule
• Two margins
  • Extensive margin: does a voter encounter proposals beyond the one that initially brought them to the platform?
  • Intensive margin: is attention concentrated on already-visible proposals, or do less prominent but potentially valuable proposals receive meaningful exposure?
• A democratic process is not judged only by how many people can participate, but by what kind of participation it enables.
  • If PB platforms fail on either margin, they deny citizens a meaningful chance to encounter alternatives and form considered judgments [9, 14].
  • Fair exposure is therefore best understood as a floor on visibility: without it, a proposal’s failure may reflect rejection, but it may equally reflect lack of exposure.

Scale creates two problems

Vetting.

• Every proposal must be assessed for feasibility, legality, cost, and duplication.
• Centralized review is not only costly, but it also concentrates agenda-setting power.
• Delegating evaluation back to citizens avoids this concentration of power, yet reintroduces the attention problem.

Scale creates two problems

PB at scale

Mechanisms for identifying weak, infeasible, duplicate, or low-quality content.

Learning from online communities